dir.lx = '../out/19.1013 tight cluster'
f.lx = file.path(dir.lx, 'landmarks_n100_k100.csv')
df.lx = read.csv(f.lx)
lx.gene = gsub("\\s*\\([^\\)]+\\)", "", df.lx$landmark)
#install.packages("gprofiler2")
library(gprofiler2)
### g:profiler query for the R result
gostres = gost(query = lx.gene, organism = "hsapiens", ordered_query = FALSE,
multi_query = FALSE, significant = T, exclude_iea = FALSE,
measure_underrepresentation = FALSE, evcodes = FALSE,
user_threshold = 0.05, correction_method = "g_SCS",
domain_scope = "annotated", custom_bg = NULL,
numeric_ns = "", sources = NULL)
Interactive plot showing gene description
### visulization capped interaction plot (p>16)
# p.capped = gostplot(gostres, capped =TRUE, interactive = T)
# p.capped
### visulization uncapped interaction plot
p.uncapped = gostplot(gostres, capped = FALSE, interactive = T)
## Warning: `group_by_()` is deprecated as of dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.
p.uncapped
cell cycle related terms
### Get cell ceycle dataframe
p = gostplot(gostres, capped =FALSE, interactive = F)
res.cellc = gostres$result[grep('cycl',gostres$result$term_name),]
# Display the cell cycle plot
p.cellc = publish_gostplot(p, res.cellc[c(1:5),],filename = NULL)
## The input 'highlight_terms' is a data.frame and therefore the column 'term_id' will be used for detection.
# Save the cell cycle plot
# p.cellc = publish_gostplot(p, res.cellc[c(1:5),],filename = 'Lx_genedesp_cellcycle.png', width = 15, height = 10)
Nucleus and lumen related terms are also enriched in Lx100 genes as in the target genes.
# GO:CC
res.cc = gostres$result[grep('GO:CC',gostres$result$source),]
p.cc = publish_gostplot(p, res.cc[c(1:8),],filename = NULL)
## The input 'highlight_terms' is a data.frame and therefore the column 'term_id' will be used for detection.
# Save the plot
# p.cc = publish_gostplot(p, res.cc[c(1:8),],width = 15, height = 10, filename = 'Lx_genedesp_GOCC.png')
Multiple protein binding function are highly enriched in GO:MF terms, including gene transcription related and kinase binding.
#GO:MF
res.mf = gostres$result[grep('GO:MF',gostres$result$source),]
p.mf = publish_gostplot(p, res.mf[c(1:10),],filename = NULL)
## The input 'highlight_terms' is a data.frame and therefore the column 'term_id' will be used for detection.
# p.mf = publish_gostplot(p, res.mf[c(1:10),],width = 15, height = 10, filename = 'Lx_genedesp_GOMF.png')
Mitochontrial related terms not enriched. The returned dataframe is empty
#mitochonrial
# res.mito = gostres$result[grep('mitochon',gostres$result$term_name),]
# p.mito = publish_gostplot(p, res.mito[c(1:5),], filename = NULL)